Frequency domain Errors-In-Variables estimation of linear dynamic systems using data from overlapping sub-records

作者: Kurt Barbe , Johan Schoukens , Rik Pintelon

DOI: 10.1109/IMTC.2007.378978

关键词:

摘要: In this paper, we study the consistency of a Frequency domain errors-ln-variables estimator using data extracted from overlapping sub-records. We show that consistent models can be found periodic excitations. Only two periods steady state response are needed to extract all required information data. This is done Moreover, system identification procedure used for independent experiments shown valid allows user reduce measurement time considerably without changing procedure.

参考文章(6)
Rik Pintelon, Johan Schoukens, Yves Rolain, Frequency-domain Approach to Continuous-time System Identification: Some Practical Aspects Springer, London. pp. 215- 248 ,(2008) , 10.1007/978-1-84800-161-9_8
Rik Pintelon, Joannes Schoukens, System Identification: A Frequency Domain Approach ,(2003)
Bernard Picinbono, Random Signals and Systems ,(1993)
J. Schoukens, R. Pintelon, G. Vandersteen, P. Guillaume, Frequency-domain system identification using non-parametric noise models estimated from a small number of data sets Automatica. ,vol. 33, pp. 1073- 1086 ,(1997) , 10.1016/S0005-1098(97)00002-2
Kurt Barbe, Johan Schoukens, Non-parametric Noise Models extracted from Overlapping Sub-records instrumentation and measurement technology conference. pp. 1758- 1763 ,(2006) , 10.1109/IMTC.2006.328227